Skip to content

Reference for ultralytics/models/yolo/pose/predict.py

Note

This file is available at https://github.com/ultralytics/ultralytics/blob/main/ultralytics/models/yolo/pose/predict.py. If you spot a problem please help fix it by contributing a Pull Request 🛠️. Thank you 🙏!


ultralytics.models.yolo.pose.predict.PosePredictor

PosePredictor(cfg=DEFAULT_CFG, overrides=None, _callbacks=None)

Bases: DetectionPredictor

A class extending the DetectionPredictor class for prediction based on a pose model.

Example
from ultralytics.utils import ASSETS
from ultralytics.models.yolo.pose import PosePredictor

args = dict(model="yolov8n-pose.pt", source=ASSETS)
predictor = PosePredictor(overrides=args)
predictor.predict_cli()
Source code in ultralytics/models/yolo/pose/predict.py
def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
    """Initializes PosePredictor, sets task to 'pose' and logs a warning for using 'mps' as device."""
    super().__init__(cfg, overrides, _callbacks)
    self.args.task = "pose"
    if isinstance(self.args.device, str) and self.args.device.lower() == "mps":
        LOGGER.warning(
            "WARNING ⚠️ Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. "
            "See https://github.com/ultralytics/ultralytics/issues/4031."
        )

postprocess

postprocess(preds, img, orig_imgs)

Return detection results for a given input image or list of images.

Source code in ultralytics/models/yolo/pose/predict.py
def postprocess(self, preds, img, orig_imgs):
    """Return detection results for a given input image or list of images."""
    preds = ops.non_max_suppression(
        preds,
        self.args.conf,
        self.args.iou,
        agnostic=self.args.agnostic_nms,
        max_det=self.args.max_det,
        classes=self.args.classes,
        nc=len(self.model.names),
    )

    if not isinstance(orig_imgs, list):  # input images are a torch.Tensor, not a list
        orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)

    results = []
    for pred, orig_img, img_path in zip(preds, orig_imgs, self.batch[0]):
        pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape).round()
        pred_kpts = pred[:, 6:].view(len(pred), *self.model.kpt_shape) if len(pred) else pred[:, 6:]
        pred_kpts = ops.scale_coords(img.shape[2:], pred_kpts, orig_img.shape)
        results.append(
            Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], keypoints=pred_kpts)
        )
    return results




📅 Created 11 months ago ✏️ Updated 1 month ago